© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45311
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ']],
    -0.96
    ']):
    -0.89
    ']);
    
    -0.88
    MigrationBuilder
    -0.86
    ']]
    -0.85
    ']}
    -0.85
    )*/
    -0.85
    }])
    -0.84
    Personensuche
    -0.83
    ])).
    -0.82
    POSITIVE LOGITS
     a
    0.98
     not
    0.85
     for
    0.80
     in
    0.80
     on
    0.79
     
    0.79
     to
    0.77
     here
    0.75
     now
    0.74
     just
    0.74
    Activations Density 0.043%

    No Known Activations